A Hierarchical Distributed Control for Power and Performances Optimization of Embedded Systems

Bellasi, Patrick; Fornaciari, William; Siorpaes, D.

doi:10.1007/978-3-642-11950-7_5

Cited by 4 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We accomplish this task by providing a runtime manager (RTM) with metadata information covering both runtime and design time knowledge of both hardware and software. The runtime management performs adaptive task mapping and scheduling [9], dynamic data management [10] and system-wide power management [11].…”

Section: Runtime Managementmentioning

confidence: 99%

“…The end result is a distributed runtime QoS Constrained Power Manager (CPM) working at the OS-level [11], based on the following concepts. System-Wide Metrics (SWMs) which are parameters describing behaviours of a running system and represent QoS requirements.…”

Section: Runtime Managementmentioning

confidence: 99%

“…The CPM model has been preliminary implemented as a Linux kernel framework (version 2.6.30) and tested under some use-cases to evaluate its overhead, which is negligible (always less than 0.01%) [11].…”

Section: Runtime Managementmentioning

confidence: 99%

See 2 more Smart Citations

2PARMA: Parallel Paradigms and Run-time Management Techniques for Many-Core Architectures

Silvano

Fornaciari

Reghizzi

et al. 2011

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

Abstract-The 2PARMA project focuses on the development of parallel programming models and run-time resource management techniques to exploit the features of many-core processor architectures.The main goals of the 2PARMA project are: the definition of a parallel programming model combining component-based and singleinstruction multiple-thread approaches, instruction set virtualisation based on portable byte-code, run-time resource management policies and mechanisms as well as design space exploration methodologies for manycore computing architectures.

show abstract

Section: Runtime Managementmentioning

confidence: 99%

Section: Runtime Managementmentioning

confidence: 99%

See 1 more Smart Citation

2PARMA: Parallel Paradigms and Run-time Management Techniques for Many-Core Architectures

Silvano

Fornaciari

Reghizzi

et al. 2011

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

show abstract

Design Space Exploration Supporting Run-Time Resource Management

Avasare

Ykman-Couvreur

Vanmeerbeeck

et al. 2011

Multi-Objective Design Space Exploration of Multiprocessor SoC Architectures

View full text Add to dashboard Cite

The ever increasing complexity and integration densities of multiprocessor systemon-chip (MPSoC) architectures, significantly enlarges the design space of embedded computing systems. A wide range of design choices must be tuned from a multiobjective perspective, mainly in terms of performance and energy consumption, to find the most suitable system configuration for the target application. Given the huge design space to be analysed, the exploration of tradeoffs between multiple competing objectives cannot be anymore driven by a manual optimisation process based on the intuition and past experience of the system architect. Multi-objective exploration of the huge design space of next generation multi/many core architectures needs for Automatic Design Space Exploration techniques to systematically explore the design choices and to compare them in terms of multiple competing objectives (trade-offs analysis). Ideally, a designer would try all possible design choices and choose the most suitable according to the specific system requirements. Unfortunately, such an exhaustive approach is often unfeasible because of the large number of design choices to be simulated and analysed, in some cases showing some sophisticated effects on system properties that rarely enable to easily and accurately model the system behavior. Consequently, good search techniques are needed not only to find design alternatives that best meet system constraints and cost criteria, but also to prune the search space to crucial parameters to enable an effective and efficient design space exploration.In the age of multi/many core architectures, system optimization and exploration definitely represent challenging research tasks. Although many point tools exist to optimize particular aspects of embedded systems, an overall design space exploration framework is needed to combine all the decisions into a global search space with a common interface to the optimization and evaluation tools. The state-of-the art lacks of a Design Space Exploration (DSE) framework to help the designer in the automatic selection of the most suitable system configuration for a certain application given a set of multiple competing objectives. ix x Preface

show abstract